© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16835
    Prev
    Next
    INDEX
    Explanations

    technical concepts and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿ľè¿ij
    -0.06
     Ø®ÙĪا
    -0.06
    hirt
    -0.06
    ç»Ļå®ļ
    -0.06
    Ø·Ùģ
    -0.06
    ayah
    -0.06
    ä¸ĭåIJĮ
    -0.06
    irit
    -0.06
    大大å°ı
    -0.06
    hoven
    -0.06
    POSITIVE LOGITS
    rons
    0.07
     (>
    0.06
    å°ij
    0.05
    离
    0.05
    æĪĸå¤ļ
    0.05
    ä¸įè§ģ
    0.05
    -held
    0.05
    olson
    0.05
    omes
    0.05
    -low
    0.05
    Activations Density 0.051%

    No Known Activations